Skip to main content

Cloudflare Observability

Connect AI tools to Cloudflare Observability to debug and get insight into your application’s logs and analytics. The Cloudflare Observability MCP server gives AI assistants secure access to observability data through the Model Context Protocol (MCP).

1. Overview​

Cloudflare Observability is a remote, vendor-hosted MCP server provided by Cloudflare. You connect to it from Cequence AI Gateway; the server uses Streamable HTTP (the standard transport for remote MCP per Cloudflare’s MCP docs).

  • Server URL: https://observability.mcp.cloudflare.com/mcp
  • Transport: HTTP (Streamable HTTP)
  • Hosted by: Cloudflare

2. Supported authentication types​

TypeSupportedNotes
OAuth 2.0YesRequired. Uses Dynamic Client Registration (DCR); sign in with your Cloudflare account.
API keyNoNot used for this remote MCP server.

When you add Cloudflare Observability in Cequence AI Gateway, authentication is handled via OAuth 2.0 with Dynamic Client Registration. You sign in with your Cloudflare account and grant access during the gateway flow.

3. What can you do with this MCP server​

With the Cloudflare Observability MCP server, you can:

  • Debug applications — Query Workers Logs and metrics to troubleshoot issues.
  • Browse invocation logs and errors — List events and browse individual request logs and errors from your Workers.
  • Compute statistics — Calculate statistics across invocations (e.g. avg, p99) via the Workers Observability API.
  • Find specific invocations — Locate individual requests matching criteria (filters on message, metadata, trigger, level, requestId, etc.).
  • Query across Workers — Query logs across all of your Workers to isolate errors and trends quickly.
  • Create visualizations — Use the telemetry data returned by the MCP server to inform new visualizations and improve observability.

4. Prerequisites​

Before adding Cloudflare Observability in Cequence AI Gateway, ensure you have:

  • Access to Cequence AI Gateway (e.g. beta.aigateway.cequence.ai)
  • A Cloudflare account with Workers / products that emit logs and metrics (e.g. Workers Analytics, Logpush, or observability features)
  • A modern browser to complete the OAuth authorization flow
  • For OAuth authentication: an auth app with client credentials (client ID and client secret) in your Cloudflare (vendor) account, unless the server supports Dynamic Client Registration (DCR).

5. Example workflows​

  • “Show errors from my Workers logs in the last hour.”
  • “Summarize request latency and error rate for [Worker name].”
  • “Find log entries containing [keyword] and explain what’s happening.”

6. Connecting MCP server from Cequence AI Gateway​

  1. Log in to Cequence AI Gateway.
  2. Choose your tenant.
  3. Go to App catalogue.
  4. Filter by Remote MCP server.
  5. Search for Cloudflare Observability and then select it.
  6. Click Create MCP server.
  7. Choose auth method. If OAuth, you need an auth app with client credentials in your vendor account (see Prerequisites).
  8. Complete the setup as prompted, select tools, and deploy.

Use the generated MCP server URL in your client as described in the Client Configuration docs. For detailed UI steps and screenshots, see Create a third-party MCP Server.

7. Additional information​